Lane line determination method and apparatus, lane line positioning accuracy evaluation method and apparatus, and device

1. A lane line determination method, comprising:

determining a line in a received road image, comprising:

determining an edge in the road image;

determining at least one line segment according to the edge; and

determining overlap portions between each of the at least one line segment with the edge, and determining the line according to the overlap portions;

screening pixels forming the line, and determining pixels forming a lane line; and

fitting the pixels forming the lane line to obtain the lane line.

2. The method according to claim 1 , wherein determining the line in the received road image further comprises:

determining a curvilinear equation of each of the overlap portions;

normalizing parameters in the curvilinear equation of each of the overlap portions; and

clustering lines corresponding to the normalized curvilinear equation to obtain a clustering result, and determining the line in the road image according to the clustering result.

3. The method according to claim 1 , wherein determining the overlap portions of each of the at least one line segment with the edge comprises:

thickening each of the at least one line segment; and

performing a logical AND operation on pixels corresponding to the thickened line segment and pixels corresponding to the edge, to determine the overlap portions.

4. The method according to claim 1 , wherein screening the pixels forming the line and determining the pixels forming the lane line comprises:

determining a principal axis according to a direction of the line;

determining a projection axis perpendicular to the principal axis;

projecting the pixels forming the line onto the projection axis; and

determining the pixels forming the lane line according to a projection result on the projection axis.

5. The method according to claim 1 , wherein the road image is an image labeled with a time stamp and acquired by image acquisition devices;

wherein four image acquisition devices are disposed on left and right sides of a target vehicle, respectively, and orientations of the image acquisition devices are perpendicular to a travelling direction of the target vehicle;

wherein fitting the pixels forming the lane line to obtain the lane line comprises:

receptively fitting pixels in the road images collected by the image acquisition devices disposed on the left and right sides of the target vehicle according to the time stamp to obtain the lane line.

6. The method according to claim 5 , wherein receptively fitting the pixels in the road images collected by the image collection devices disposed on the left and right sides of the target vehicle respectively comprises:

fitting the pixels in the road images collected by the image collection devices disposed on the left and right sides of the target vehicle according to a minimum slope error, so that slope errors of lane lines on the left and right sides of the target vehicle after the fitting are within an allowable range.

7. A lane line positioning accuracy evaluation method, comprising:

acquiring a detection value of the lane line to be evaluated;

acquiring a true value of the lane line, wherein the true value is obtained by the method according to claim 1 ; and

evaluating a detection value of the lane line to be evaluated according to an error between the detection value of the lane line and the true value of the lane line.

8. The method according to claim 7 , wherein determining the error between the detection value of the lane line and the true value of the lane line comprises:

calculating a lateral difference between the detection value of the lane line and true value of the lane line, and/or

calculating a heading angle difference between the detection value of the lane line and the true value of the lane line; and

taking the lateral difference and/or the heading angle difference as the error between the detection value of the lane line and the true value of the lane line.

9. The method according to claim 7 , wherein the detection value of the lane line to be evaluated is obtained according to a high-precision map positioning algorithm.

10. A non-transitory computer readable storage medium for storing computer instructions, wherein the computer instructions, when executed by a computer, cause the computer to perform the method according to claim 7 .

11. A non-transitory computer readable storage medium for storing computer instructions, wherein the computer instructions, when executed by a computer, cause the computer to perform the method according to claim 1 .

12. A lane line determination apparatus, comprising:

at least one processor; and

a memory communicatively connected to the at least one processor, wherein

the memory stores instructions executable by the at least one processor, the instructions are executed by the at least one processor to enable the at least one processor to:

determine a line in a received road image, where the instructions are executed by the at least one processor to enable the at least one processor to:

determine an edge in the road image;

determine at least one line segment according to the edge; and

determine overlap portions of each of the at least one line segment with the edge, and determine the line according to the overlap portions;

screen pixels forming the line and determine pixels forming a lane line; and

fit the pixels forming the lane line to obtain the lane line.

13. The apparatus according to claim 12 , wherein the instructions are executed by the at least one processor to enable the at least one processor further to:

determine a curvilinear equation of each of the overlap portions;

normalize parameters in the curvilinear equation of each of the overlap portions; and

cluster lines corresponding to the normalized curvilinear equation to obtain a clustering result, and determine the line in the road image according to the clustering result.

14. The apparatus according to claim 12 , wherein the instructions are executed by the at least one processor to enable the at least one processor further to:

thicken each of the at least one line segment; and

perform a logical AND operation on pixels corresponding to the thickened line segment and pixels corresponding to the edge, to determine the overlap portions.

15. The apparatus according to claim 12 , wherein the instructions are executed by the at least one processor to enable the at least one processor further to:

determine a principal axis according to a direction of the line;

determine a projection axis perpendicular to the principal axis;

project the pixels forming the line onto the projection axis; and

determine the pixels forming the lane line according to a projection result on the projection axis.

16. The apparatus according to claim 12 , wherein the road image is an image labeled with a time stamp and acquired by image acquisition devices;

wherein four image acquisition devices are disposed on left and right sides of a target vehicle, respectively, and orientations of the image acquisition devices are perpendicular to a travelling direction of the target vehicle;

wherein the instructions are executed by the at least one processor to enable the at least one processor further to respectively fit the pixels in the road images collected by the image acquisition devices disposed on the left and right sides of the target vehicle according to the time stamp to obtain the lane line.

17. A lane line positioning accuracy evaluation apparatus, comprising:

at least one processor; and

a memory communicatively connected to the at least one processor, wherein

the memory stores instructions executable by the at least one processor, the instructions are executed by the at least one processor to enable the at least one processor to:

acquire a detection value of a lane line to be evaluated;

acquire a true value of the lane line obtained by the apparatus according to claim 12 ; and

evaluate the detection value of the lane line to be evaluated according to an error between the detection value of the lane line and the true value of the lane line.

18. The apparatus according to claim 17 , wherein the instructions are executed by the at least one processor to enable the at least one processor further to:

calculate a lateral difference between the detection value of the lane line and the true value of the lane line, and/or

calculate a heading angle difference between the detection value of the lane line and the true value of the lane line; and

the lateral difference and/or the heading angle difference is taken as the error between the detection value of the lane line and the true value of the lane line.